Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 0.9965 | $2541.33 | 1210.9M | 2.5M | 19h 50m | 2830 | 27 |
| 2 | GPT-6 Astra | 0.9845 | $2685.88 | 1278.3M | 2.6M | 20h 0m | 2961 | 38 |
| 3 | GPT-6 Astra | 0.9844 | $2735.71 | 1297.4M | 2.6M | 19h 42m | 2884 | 29 |
| 4 | GPT-6 Astra | 0.9841 | $2589.72 | 1228.2M | 2.6M | 19h 59m | 2801 | 34 |
| 5 | GPT-6 Astra | 0.9841 | $2728.19 | 1288.8M | 2.7M | 19h 57m | 2941 | 47 |
| 6 | Gemini 4 Argon | 0.9334 | $206.78 | 382.0M | 1.3M | 15h 47m | 877 | 5 |
| 7 | Claude Opus 5.5 | 0.9097 | $156.04 | 545.9M | 1.3M | 19h 52m | 1288 | 19 |
| 8 | Claude Sonnet 5.5 | 0.9083 | $181.73 | 740.0M | 2.3M | 18h 47m | 1546 | 6 |
| 9 | Gemini 4 Argon | 0.9080 | $207.90 | 379.4M | 1.5M | 15h 34m | 854 | 10 |
| 10 | Claude Sonnet 5.5 | 0.8981 | $169.21 | 677.4M | 2.4M | 19h 40m | 1549 | 4 |
| 11 | Claude Opus 5.5 | 0.8821 | $144.22 | 511.3M | 1.0M | 18h 11m | 1074 | 26 |
| 12 | Claude Opus 5.5 | 0.8618 | $140.79 | 553.3M | 1.1M | 19h 44m | 1191 | 4 |
| 13 | Claude Opus 5.5 | 0.8540 | $182.36 | 671.0M | 1.3M | 19h 5m | 1637 | 23 |
| 14 | Gemini 4 Argon | 0.8458 | $261.90 | 442.3M | 1.8M | 19h 2m | 1056 | 6 |
| 15 | Claude Sonnet 5.5 | 0.7941 | $169.89 | 694.5M | 2.3M | 19h 11m | 1580 | 2 |
| 16 | Gemini 4 Argon | 0.7148 | $130.35 | 185.9M | 816k | 8h 32m | 449 | 3 |
| 17 | Gemini 4 Argon | 0.7072 | $170.81 | 258.5M | 1.2M | 8h 45m | 673 | 3 |
| 18 | Claude Sonnet 5.5 | 0.7057 | $164.69 | 656.9M | 2.0M | 19h 44m | 1566 | 6 |
| 19 | Claude Sonnet 5.5 | 0.6877 | $201.48 | 823.9M | 2.7M | 19h 38m | 1897 | 8 |
| 20 | Claude Opus 5.5 | 0.6632 | $158.77 | 603.5M | 1.1M | 18h 8m | 1203 | 7 |
| 21 | Claude Fable 5.1 | 0.4716 | $208.91 | 376.5M | 866k | 17h 50m | 1017 | 10 |
| 22 | Claude Fable 5.1 | 0.3532 | $168.41 | 314.0M | 539k | 12h 53m | 608 | 4 |
| 23 | Claude Fable 5.1 | 0.3481 | $106.70 | 193.6M | 429k | 9h 8m | 454 | 13 |
| 24 | Claude Fable 5.1 | 0.3402 | $125.75 | 229.9M | 473k | 10h 25m | 482 | 6 |
| 25 | Claude Opus 5 | 0.2471 | $159.25 | 261.3M | 595k | 19h 14m | 530 | 3 |
| 26 | GPT-5.6 Sol | 0.2171 | $270.86 | 274.0M | 362k | 12h 30m | 806 | 4 |
| 27 | Claude Haiku 5.5 | 0.2045 | $31.05 | 511.9M | 1.8M | 18h 49m | 1138 | 3 |
| 28 | Claude Opus 5 | 0.2039 | $238.32 | 344.9M | 699k | 19h 25m | 735 | 12 |
| 29 | Claude Fable 5.1 | 0.1985 | $113.40 | 205.2M | 463k | 5h 28m | 430 | 3 |
| 30 | Claude Fable 5 | 0.1934 | $427.55 | 353.3M | 996k | 18h 35m | 924 | 3 |
| 31 | Claude Haiku 5.5 | 0.1872 | $31.43 | 521.7M | 1.9M | 17h 21m | 1152 | 5 |
| 32 | Claude Opus 5 | 0.1567 | $190.60 | 308.2M | 776k | 19h 30m | 742 | 5 |
| 33 | GPT-5.6 Sol | 0.1552 | $336.67 | 340.6M | 347k | 11h 28m | 906 | 14 |
| 34 | Claude Fable 5 | 0.1550 | $396.50 | 323.2M | 982k | 19h 5m | 848 | 7 |
| 35 | Grok 4.7 | 0.1336 | $487.10 | 480.1M | 1.3M | 20h 1m | 1837 | 77 |
| 36 | Claude Fable 5 | 0.1319 | $351.84 | 291.9M | 807k | 19h 38m | 711 | 8 |
| 37 | Claude Opus 5 | 0.1302 | $226.32 | 342.2M | 722k | 19h 35m | 760 | 14 |
| 38 | GPT-5.6 Sol | 0.1222 | $253.61 | 257.1M | 305k | 8h 28m | 760 | 3 |
| 39 | Grok 4.7 | 0.1182 | $509.72 | 506.8M | 1.5M | 18h 52m | 2068 | 85 |
| 40 | Grok 4.7 | 0.1138 | $588.60 | 597.8M | 1.8M | 19h 55m | 2409 | 106 |
| 41 | GPT-5.6 Sol | 0.1119 | $309.74 | 312.3M | 342k | 9h 22m | 857 | 12 |
| 42 | Muse Spark 1.3 | 0.1055 | $206.91 | 689.2M | 886k | 10h 35m | 1681 | 1 |
| 43 | GPT-5.6 Sol | 0.1032 | $420.32 | 406.2M | 354k | 11h 35m | 880 | 13 |
| 44 | Claude Fable 5 | 0.0950 | $314.88 | 250.5M | 673k | 18h 55m | 484 | 7 |
| 45 | Claude Haiku 5.5 | 0.0884 | $18.09 | 294.8M | 1.2M | 8h 15m | 682 | 4 |
| 46 | Claude Haiku 5.5 | 0.0726 | $19.59 | 319.7M | 1.3M | 12h 4m | 710 | 5 |
| 47 | Grok 4.7 | 0.0713 | $540.56 | 547.5M | 1.5M | 19h 14m | 2247 | 102 |
| 48 | Grok 4.6 | 0.0526 | $317.62 | 274.4M | 1.8M | 19h 55m | 1078 | 110 |
| 49 | Muse Spark 1.3 | 0.0410 | $299.15 | 649.2M | 932k | 19h 37m | 1588 | 2 |
| 50 | Muse Spark 1.3 | 0.0386 | $233.75 | 628.1M | 517k | 18h 2m | 1282 | 5 |
| 51 | Grok 4.6 | 0.0382 | $286.38 | 260.8M | 1.4M | 19h 57m | 984 | 103 |
| 52 | Gemini 3.8 Flash | 0.0349 | $41.18 | 386.0M | 562k | 10h 22m | 970 | 4 |
| 53 | Grok 4.6 | 0.0273 | $488.84 | 437.7M | 2.0M | 19h 56m | 1536 | 307 |
| 54 | Grok 4.6 | 0.0266 | $454.46 | 403.4M | 2.0M | 19h 58m | 1435 | 75 |
| 55 | Muse Spark 1.3 | 0.0254 | $147.68 | 673.6M | 1.0M | 19h 47m | 1561 | 8 |
| 56 | Muse Spark 1.3 | 0.0250 | $351.72 | 511.0M | 807k | 19h 59m | 1300 | 1 |
| 57 | Kimi K3 | 0.0249 | $126.07 | 350.4M | 1.1M | 19h 56m | 936 | 7 |
| 58 | Claude Opus 5 | 0.0249 | $181.57 | 297.4M | 666k | 19h 31m | 602 | 6 |
| 59 | Kimi K3 | 0.0214 | $168.60 | 476.4M | 1.3M | 20h 1m | 1079 | 5 |
| 60 | Grok 4.7 | 0.0196 | $518.13 | 515.0M | 1.7M | 19h 40m | 2079 | 58 |
| 61 | GLM-5.3 | 0.0166 | $91.30 | 316.9M | 852k | 19h 35m | 891 | 7 |
| 62 | Grok 4.6 | 0.0147 | $328.36 | 283.8M | 1.8M | 19h 57m | 1084 | 57 |
| 63 | Claude Haiku 5.5 | 0.0140 | $10.65 | 174.9M | 638k | 2h 59m | 351 | 5 |
| 64 | Gemini 3.8 Flash | 0.0130 | $23.89 | 196.2M | 401k | 6h 33m | 507 | 3 |
| 65 | Gemini 3.7 Flash | 0.0116 | $11.28 | 68.7M | 237k | 4h 7m | 304 | 2 |
| 66 | Kimi K3 | 0.0104 | $167.00 | 460.9M | 1.4M | 20h 1m | 1039 | 1 |
| 67 | Gemini 3.8 Flash | 0.0089 | $32.30 | 275.0M | 453k | 6h 8m | 610 | 4 |
| 68 | Kimi K3 | 0.0079 | $184.18 | 516.4M | 1.3M | 19h 37m | 1094 | 2 |
| 69 | DeepSeek V4 Flash Vision Exp | 0.0069 | $10.96 | 663.9M | 1.1M | 19h 2m | 1527 | 2 |
| 70 | DeepSeek V4 Flash Vision Exp | 0.0065 | $10.60 | 633.4M | 1.1M | 15h 56m | 1516 | 8 |
| 71 | Gemini 3.7 Flash | 0.0064 | $35.75 | 195.3M | 360k | 8h 28m | 555 | 1 |
| 72 | GLM-5.3 | 0.0054 | $111.06 | 362.5M | 755k | 19h 29m | 893 | 10 |
| 73 | Gemini 3.7 Flash | 0.0054 | $6.52 | 51.3M | 224k | 2h 40m | 274 | 2 |
| 74 | GLM-5.3 | 0.0038 | $97.66 | 297.0M | 573k | 19h 4m | 633 | 5 |
| 75 | DeepSeek V4 Flash Vision Exp | 0.0028 | $12.40 | 756.6M | 1.2M | 19h 8m | 1756 | 39 |
| 76 | DeepSeek V4 Flash Vision Exp | 0.0027 | $6.77 | 415.2M | 638k | 18h 28m | 837 | 7 |
| 77 | Gemini 3.7 Flash | 0.0020 | $17.05 | 105.9M | 300k | 5h 32m | 381 | 1 |
| 78 | Qwen3.8-Max | 0.0018 | $183.02 | 558.1M | 1.7M | 19h 56m | 1375 | 1 |
| 79 | Qwen3.8-Max | 0.0016 | $153.43 | 448.8M | 1.7M | 19h 59m | 1202 | 1 |
| 80 | GLM-5.3 Flash | 0.0015 | $14.67 | 306.8M | 449k | 20h 1m | 746 | 1 |
| 81 | Qwen3.8-Max | 0.0010 | $149.46 | 419.0M | 1.2M | 19h 25m | 993 | 2 |
| 82 | GLM-5.3 Flash | 0.0010 | $16.55 | 339.1M | 548k | 17h 44m | 740 | 5 |
| 83 | Gemini 3.7 Flash | 0.0009 | $11.28 | 77.4M | 230k | 5h 1m | 369 | 3 |
| 84 | Gemini 3.8 Flash | 0.0007 | $23.00 | 212.3M | 376k | 5h 7m | 526 | 3 |
| 85 | GLM-5.3 | 0.0006 | $94.18 | 300.9M | 621k | 18h 57m | 592 | 10 |
| 86 | GLM-5.3 Flash | 0.0002 | $12.16 | 275.0M | 487k | 19h 36m | 628 | 3 |
| 87 | GLM-5.3 Flash | 0.0001 | $17.12 | 399.9M | 616k | 15h 49m | 828 | 5 |
| 88 | Qwen3.8-Max | 0.0001 | $169.64 | 519.3M | 1.6M | 20h 0m | 1239 | 1 |
| 89 | Muse Spark 1.2 | 0.0000 | $7.77 | 40.8M | 287k | 2h 9m | 182 | 5 |
| 90 | Inkling | 0.0000 | $6.72 | 7.0M | 25k | 22m | 138 | 2 |
| 91 | Qwen3.8-Max | 0.0000 | $189.91 | 559.5M | 1.9M | 19h 51m | 1464 | 3 |
| 92 | Kimi K3 | 0.0000 | $182.81 | 498.0M | 1.4M | 20h 1m | 1063 | 2 |
| 93 | Muse Spark 1.2 | 0.0000 | $8.07 | 38.9M | 412k | 3h 7m | 202 | 4 |
| 94 | DeepSeek V4 Flash Vision Exp | 0.0000 | $11.01 | 666.7M | 1.1M | 19h 11m | 1467 | 11 |
| 95 | Qwen3.8-Max-0902 | 0.0000 | $58.14 | 147.3M | 957k | 20h 6m | 434 | 1 |
| 96 | Qwen3.8-Max-0902 | 0.0000 | $33.94 | 103.0M | 952k | 20h 7m | 367 | 1 |
| 97 | Muse Spark 1.2 | 0.0000 | $6.30 | 24.2M | 135k | 1h 37m | 159 | 4 |
| 98 | Qwen3.8-Max-0902 | 0.0000 | $41.85 | 96.9M | 886k | 20h 4m | 414 | 1 |
| 99 | Claude Fable 5 | 0.0000 | $411.65 | 293.0M | 731k | 19h 45m | 698 | 3 |
| 100 | GLM-5.3 | 0.0000 | $103.09 | 375.1M | 554k | 19h 46m | 790 | 12 |
| 101 | Gemini 3.8 Flash | 0.0000 | $53.67 | 394.0M | 628k | 13h 26m | 1068 | 4 |
| 102 | Inkling | 0.0000 | $6.59 | 6.8M | 31k | 2h 10m | 146 | 2 |
| 103 | Muse Spark 1.2 | 0.0000† | $2.64 | 12.4M | 42k | 2h 25m | 90 | 2 |
| 104 | Qwen3.8-Max-0902 | 0.0000 | $50.29 | 127.1M | 914k | 20h 7m | 479 | 1 |
| 105 | Inkling | 0.0000 | $6.57 | 6.8M | 31k | 35m | 156 | 1 |
| 106 | GLM-5.3 Flash | 0.0000 | $17.57 | 389.3M | 753k | 20h 0m | 891 | 8 |
| 107 | Qwen3.8-Max-0902 | 0.0000 | $56.38 | 146.6M | 1.2M | 20h 0m | 468 | 1 |
| 108 | Inkling | 0.0000 | $4.24 | 4.4M | 17k | 41m | 109 | 1 |
| 109 | Inkling | 0.0000 | $8.87 | 9.2M | 43k | 1h 49m | 170 | 2 |
| 110 | Muse Spark 1.2 | 0.0000† | $1.72 | 8.1M | 39k | 1h 17m | 88 | 1 |
† score adjusted by manual review; the trace's Judge tab carries the measured score and the rationale.